mirror of
https://github.com/mikegerber/ocrd_calamari.git
synced 2025-06-08 19:29:53 +02:00
✨ Allow controlling of output hierarchy level, e.g. only line, not words+glyphs
This commit is contained in:
parent
0f0bae18ba
commit
ef3fb44fb5
4 changed files with 73 additions and 37 deletions
12
README.md
12
README.md
|
@ -13,10 +13,11 @@ This offers a OCR-D compliant workspace processor for some of the functionality
|
||||||
This processor only operates on the text line level and so needs a line segmentation (and by extension a binarized
|
This processor only operates on the text line level and so needs a line segmentation (and by extension a binarized
|
||||||
image) as its input.
|
image) as its input.
|
||||||
|
|
||||||
In addition to the line text it also outputs glyph segmentation including
|
In addition to the line text it may also output word and glyph segmentation
|
||||||
per-glyph confidence values and per-glyph alternative predictions as provided by
|
including per-glyph confidence values and per-glyph alternative predictions as
|
||||||
the Calamari OCR engine. Note that while Calamari does not provide word
|
provided by the Calamari OCR engine, using a `textequiv_level` of `word` or
|
||||||
segmentation, this processor produces word segmentation inferred from text
|
`glyph`. Note that while Calamari does not provide word segmentation, this
|
||||||
|
processor produces word segmentation inferred from text
|
||||||
segmentation and the glyph positions. The provided glyph and word segmentation
|
segmentation and the glyph positions. The provided glyph and word segmentation
|
||||||
can be used for text extraction and highlighting, but is probably not useful for
|
can be used for text extraction and highlighting, but is probably not useful for
|
||||||
further image-based processing.
|
further image-based processing.
|
||||||
|
@ -53,7 +54,8 @@ ocrd-calamari-recognize -p test-parameters.json -m mets.xml -I OCR-D-SEG-LINE -O
|
||||||
With `test-parameters.json`:
|
With `test-parameters.json`:
|
||||||
~~~
|
~~~
|
||||||
{
|
{
|
||||||
"checkpoint": "/path/to/some/trained/models/*.ckpt.json"
|
"checkpoint": "/path/to/some/trained/models/*.ckpt.json",
|
||||||
|
"textequiv_level": "line",
|
||||||
}
|
}
|
||||||
~~~
|
~~~
|
||||||
|
|
||||||
|
|
|
@ -25,6 +25,12 @@
|
||||||
"voter": {
|
"voter": {
|
||||||
"description": "The voting algorithm to use",
|
"description": "The voting algorithm to use",
|
||||||
"type": "string", "default": "confidence_voter_default_ctc"
|
"type": "string", "default": "confidence_voter_default_ctc"
|
||||||
|
},
|
||||||
|
"textequiv_level": {
|
||||||
|
"type": "string",
|
||||||
|
"enum": ["line", "word", "glyph"],
|
||||||
|
"default": "line",
|
||||||
|
"description": "Deepest PAGE XML hierarchy level to include TextEquiv results for"
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -120,6 +120,7 @@ class CalamariRecognize(Processor):
|
||||||
spaces = (c == ' ')
|
spaces = (c == ' ')
|
||||||
yield word
|
yield word
|
||||||
|
|
||||||
|
if self.parameter['textequiv_level'] in ['word', 'glyph']:
|
||||||
word_no = 0
|
word_no = 0
|
||||||
i = 0
|
i = 0
|
||||||
|
|
||||||
|
@ -137,6 +138,7 @@ class CalamariRecognize(Processor):
|
||||||
word = WordType(id='%s_word%04d' % (line.id, word_no), Coords=CoordsType(points))
|
word = WordType(id='%s_word%04d' % (line.id, word_no), Coords=CoordsType(points))
|
||||||
word.add_TextEquiv(TextEquivType(Unicode=word_text))
|
word.add_TextEquiv(TextEquivType(Unicode=word_text))
|
||||||
|
|
||||||
|
if self.parameter['textequiv_level'] == 'glyph':
|
||||||
for glyph_no, p in enumerate(word_positions):
|
for glyph_no, p in enumerate(word_positions):
|
||||||
glyph_start = p.global_start
|
glyph_start = p.global_start
|
||||||
glyph_end = p.global_end
|
glyph_end = p.global_end
|
||||||
|
|
|
@ -87,6 +87,7 @@ def test_word_segmentation(workspace):
|
||||||
output_file_grp="OCR-D-OCR-CALAMARI",
|
output_file_grp="OCR-D-OCR-CALAMARI",
|
||||||
parameter={
|
parameter={
|
||||||
"checkpoint": CHECKPOINT,
|
"checkpoint": CHECKPOINT,
|
||||||
|
"textequiv_level": "word", # Note that we're going down to word level here
|
||||||
}
|
}
|
||||||
).process()
|
).process()
|
||||||
workspace.save_mets()
|
workspace.save_mets()
|
||||||
|
@ -106,5 +107,30 @@ def test_word_segmentation(workspace):
|
||||||
line_text = line.xpath("pc:TextEquiv/pc:Unicode", namespaces=NSMAP)[0].text
|
line_text = line.xpath("pc:TextEquiv/pc:Unicode", namespaces=NSMAP)[0].text
|
||||||
assert words_text == line_text
|
assert words_text == line_text
|
||||||
|
|
||||||
|
# For extra measure, check that we're not seeing any glyphs, as we asked for textequiv_level == "word"
|
||||||
|
glyphs = tree.xpath("//pc:Glyph", namespaces=NSMAP)
|
||||||
|
assert len(glyphs) == 0
|
||||||
|
|
||||||
|
|
||||||
|
def test_glyphs(workspace):
|
||||||
|
CalamariRecognize(
|
||||||
|
workspace,
|
||||||
|
input_file_grp="OCR-D-GT-SEG-LINE",
|
||||||
|
output_file_grp="OCR-D-OCR-CALAMARI",
|
||||||
|
parameter={
|
||||||
|
"checkpoint": CHECKPOINT,
|
||||||
|
"textequiv_level": "glyph", # Note that we're going down to glyph level here
|
||||||
|
}
|
||||||
|
).process()
|
||||||
|
workspace.save_mets()
|
||||||
|
|
||||||
|
page1 = os.path.join(workspace.directory, "OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_0001.xml")
|
||||||
|
assert os.path.exists(page1)
|
||||||
|
tree = etree.parse(page1)
|
||||||
|
|
||||||
|
# The result should contain a lot of glyphs
|
||||||
|
glyphs = tree.xpath("//pc:Glyph", namespaces=NSMAP)
|
||||||
|
assert len(glyphs) >= 100
|
||||||
|
|
||||||
|
|
||||||
# vim:tw=120:
|
# vim:tw=120:
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue